© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 8933
    Prev
    Next
    INDEX
    Explanations

    output signal, size, file, clock

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/olmo-3-saes/olmo-3-1025-7b
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    稿
    -0.11
    ris
    -0.10
    tas
    -0.09
     gaz
    -0.09
    iest
    -0.09
    adir
    -0.09
    onga
    -0.09
    emi
    -0.09
    abar
    -0.09
     succeeding
    -0.09
    POSITIVE LOGITS
    combe
    0.09
     Zuk
    0.08
     Hemisphere
    0.08
    ãģĽ
    0.07
    ting
    0.07
     Rut
    0.07
    åĵģ
    0.07
     stud
    0.07
     rut
    0.07
    ILT
    0.07
    Activations Density 0.173%

    No Known Activations